Title :
Signal combination and classification scheme for neural networks
Author :
Xu, Shenchu ; Dong, Jyang
Author_Institution :
Dept. of Phys., Fujian Normal Univ., Fuzhou, China
Abstract :
The signal combinations are made as the stable attractors of the Hopfield (1982) model neural networks by using the methods of combinatorial optimization, then the classification scheme of binary numbers in the corresponding neural networks with a single-variance of the synaptic matrix elements is summarized and synthesized by the method which we borrowed from the Fu-Xi´s position on eight trigrams in I-ching (theory of changes)
Keywords :
Hopfield neural nets; combinatorial mathematics; matrix algebra; optimisation; signal processing; Hopfield model neural networks; binary numbers classification; combinatorial optimization; neural networks; signal combinations; stable attractors; synaptic matrix elements; theory of changes; trigrams; Binary search trees; Circuit synthesis; Hopfield neural networks; Model driven engineering; Network synthesis; Neural networks; Neurons; Optimization methods;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.571158
